implement-epic

implement-epic is a command for Claude Code from marcusgoll/Spec-Flow. It costs 0 tokens per session (11,956 once invoked), scanned C, original, MIT.

A command for carrying out several sprints from an existing sprint plan at the same time when their dependencies allow it. It uses separate work areas and records results such as completed tasks, API agreements, and status.

In plain words
What is it for?
Use it to execute an epic's sprint plan, run independent sprint work in parallel, follow dependency layers, and produce sprint and audit records.
Why use it?
It reduces waiting when independent parts of a large project can be developed concurrently, while keeping dependencies and progress visible.

Command for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/marcusgoll/spec-flow/implement-epic-legacy
Clone the repo
git clone --depth 1 https://github.com/marcusgoll/Spec-Flow

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for implement-epic

README.md
[![agentmods](https://agentmods.dev/badge/commands/marcusgoll/spec-flow/implement-epic-legacy.svg)](https://agentmods.dev/commands/marcusgoll/spec-flow/implement-epic-legacy)
Your own site
<a href="https://agentmods.dev/commands/marcusgoll/spec-flow/implement-epic-legacy"><img src="https://agentmods.dev/badge/commands/marcusgoll/spec-flow/implement-epic-legacy.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 11,956 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.11956
Opus 5 $0.00000 $0.05978
Sonnet 5 $0.00000 $0.02391
Haiku 4.5 $0.00000 $0.01196

Measured 4d ago against content hash 7c81568f6657, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

implement-epic scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

`cd ${sprintDir} && rm -rf .next .cache coverage node_modules/.cache`

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

execSync(
.claude/commands/_archived/implement-epic-legacy.md · 1,579 lines

How it starts

The opening of the file, as written. The whole thing — 1,579 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/implement-epic — Parallel Sprint Execution

Current Branch: !git branch --show-current 2>/dev/null || echo "none"

Epic Directory: !ls -d epics/*/ 2>/dev/null | head -1 | xargs basename 2>/dev/null || echo "none"

Worktree Context: !bash .spec-flow/scripts/bash/worktree-context.sh info 2>/dev/null || echo '{"is_worktree": false}'

Worktree Auto-Create: !bash .spec-flow/scripts/utils/load-preferences.sh --key "worktrees.auto_create" --default "true" 2>/dev/null || echo "true"

Sprint Plan: @epics/*/sprint-plan.md

Total Sprints: !grep -c "^## Sprint S" epics/*/sprint-plan.md 2>/dev/null || echo "0"

Execution Layers: !grep -c "^| Layer |" epics/*/sprint-plan.md 2>/dev/null || echo "0"

Locked Contracts: !grep -c "^####.*Contract" epics/*/sprint-plan.md 2>/dev/null || echo "0"

Git Status: !git status --short 2>/dev/null || echo "clean"

Epic Artifacts (after execution):

  • @epics//sprints/S/tasks.md (completed tasks per sprint)
  • @epics//contracts/.yaml (locked API contracts)
  • @epics/*/state.yaml (epic status)
  • @epics/*/audit-report.xml (effectiveness metrics)

Parallel sprint execution workflow:

  1. Detect epic workspace and load sprint-plan.md
  2. Validate sprint directories, tasks, and contract files
  3. Execute layers sequentially (sprints within layer run in parallel)
  4. Launch specialist agents per sprint subsystem
  5. Monitor progress and consolidate results
  6. Auto-trigger workflow audit after completion
  7. Present epic summary with velocity metrics

Key principles:

  • Dependency-driven parallelism: Layers execute sequentially, sprints within layer run in parallel
  • Contract locking: API contracts locked before implementation to enable parallel work
  • Specialist routing: Backend sprints → backend-dev agent, Frontend → frontend-dev, etc.
  • True parallel execution: SINGLE message with multiple Task tool calls
  • Automatic auditing: Effectiveness metrics captured after implementation

Workflow position: epic → clarify → plan → tasks → implement-epic → optimize → preview → ship

Read the full file on GitHub · 1,579 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 1,579 lines · 0 tokens per session scan C 7c81568f6657

Subscribe to this mod's changes

implement-epic is a command published in the GitHub repository marcusgoll/Spec-Flow (92 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 11,956 tokens. A static security scan graded it C with 2 findings (recursive force delete, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.